Hugging Face's logo

BDAIO
/
result-colab

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
BDAIO commited on
Commit
d8f88f7
•
1 Parent(s): c839dc0

End of training

Browse files
Files changed (3) hide show
  1. README.md +18 -23
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3751
24
- - Accuracy: 0.8853
25
- - Precision: 0.8785
26
- - Recall: 0.8773
27
- - F1: 0.8773
28
 
29
  ## Model description
30
 
@@ -44,32 +44,27 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
- - train_batch_size: 32
48
- - eval_batch_size: 32
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
52
- - num_epochs: 15
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
- | 1.3635 | 1.0 | 48 | 1.1593 | 0.5963 | 0.4671 | 0.5259 | 0.4501 |
59
- | 0.9895 | 2.0 | 96 | 0.7987 | 0.6881 | 0.6824 | 0.6271 | 0.6017 |
60
- | 0.6845 | 3.0 | 144 | 0.6432 | 0.7523 | 0.7789 | 0.7076 | 0.7071 |
61
- | 0.5856 | 4.0 | 192 | 0.5896 | 0.7844 | 0.8315 | 0.7457 | 0.7463 |
62
- | 0.4328 | 5.0 | 240 | 0.4232 | 0.8716 | 0.8750 | 0.8585 | 0.8645 |
63
- | 0.4298 | 6.0 | 288 | 0.4118 | 0.8853 | 0.8783 | 0.8810 | 0.8789 |
64
- | 0.322 | 7.0 | 336 | 0.3988 | 0.8807 | 0.8824 | 0.8655 | 0.8712 |
65
- | 0.3561 | 8.0 | 384 | 0.4169 | 0.8716 | 0.8630 | 0.8679 | 0.8637 |
66
- | 0.27 | 9.0 | 432 | 0.3779 | 0.8991 | 0.8972 | 0.8913 | 0.8938 |
67
- | 0.2472 | 10.0 | 480 | 0.3850 | 0.8991 | 0.8928 | 0.8942 | 0.8924 |
68
- | 0.2349 | 11.0 | 528 | 0.3749 | 0.8945 | 0.8855 | 0.8919 | 0.8875 |
69
- | 0.2491 | 12.0 | 576 | 0.3798 | 0.9037 | 0.8969 | 0.8992 | 0.8975 |
70
- | 0.2239 | 13.0 | 624 | 0.3778 | 0.8853 | 0.8783 | 0.8810 | 0.8793 |
71
- | 0.2276 | 14.0 | 672 | 0.3755 | 0.8899 | 0.8827 | 0.8823 | 0.8822 |
72
- | 0.206 | 15.0 | 720 | 0.3751 | 0.8853 | 0.8785 | 0.8773 | 0.8773 |
73
 
74
 
75
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3660
24
+ - Accuracy: 0.8991
25
+ - Precision: 0.8990
26
+ - Recall: 0.8942
27
+ - F1: 0.8959
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
+ - train_batch_size: 64
48
+ - eval_batch_size: 64
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
52
+ - num_epochs: 10
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.3839 | 1.0 | 24 | 0.4077 | 0.8716 | 0.8635 | 0.8717 | 0.8639 |
59
+ | 0.3268 | 2.0 | 48 | 0.4052 | 0.8578 | 0.8510 | 0.8489 | 0.8467 |
60
+ | 0.2524 | 3.0 | 72 | 0.4014 | 0.8899 | 0.8938 | 0.8795 | 0.8843 |
61
+ | 0.2171 | 4.0 | 96 | 0.3582 | 0.8899 | 0.8860 | 0.8849 | 0.8846 |
62
+ | 0.1712 | 5.0 | 120 | 0.3983 | 0.8899 | 0.8885 | 0.8804 | 0.8826 |
63
+ | 0.1627 | 6.0 | 144 | 0.3789 | 0.8991 | 0.8984 | 0.8998 | 0.8983 |
64
+ | 0.1462 | 7.0 | 168 | 0.3884 | 0.8991 | 0.9004 | 0.8922 | 0.8955 |
65
+ | 0.1499 | 8.0 | 192 | 0.3727 | 0.9083 | 0.9069 | 0.9080 | 0.9070 |
66
+ | 0.1557 | 9.0 | 216 | 0.3669 | 0.8991 | 0.8990 | 0.8942 | 0.8959 |
67
+ | 0.1462 | 10.0 | 240 | 0.3660 | 0.8991 | 0.8990 | 0.8942 | 0.8959 |
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d79bd51370f31d48ea0de60a3293a1cf9c445b1540288efaebc20d0f52e7c989
3
  size 2027820436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816315d73be3ea762cf88da7527d6e0423aca3180e45e1195ff2d5905c765405
3
  size 2027820436
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:716937c1b15324b985dc0cb8be786f4a6dc58f5fb6d4e1c98ab265a8e4bfb6e6
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3393f5c9f6f341e2075825ca69dbdceff1327fc04633c92aa44d60cd057ad9e2
3
  size 5048